convez.ai
MCP ServerAutomaçãoAvançado
itlackey

AKM — Agent Kit Manager

itlackey/akm

Gerenciador de pacotes para capabilities de agentes IA com busca unificada

Ver no GitHub
BomPluginScore · de 0 a 100

Gerenciador de pacotes para skills, comandos, ferramentas e conhecimento de agentes de IA. Integra fontes locais, repositórios GitHub, pacotes npm e websites em um índice unificado pesquisável, permitindo que agentes recuperem exatamente o que precisam sob demanda.

Instalação

$npx convez-ai itlackey/akm

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
70
Forks
4
Acompanhando
1
Saúde
85%
Último commit
há 1 dia
Versão
v0.10.261129
Issues abertas
19
Contribuidores
6

Casos de uso

  • Organizar e versionar skills e workflows para múltiplos agentes
  • Criar uma base de conhecimento curada acessível por CLI para assistentes de código
  • Melhorar continuamente a qualidade de assets através de feedback estruturado

Veredito

AKM é um sistema robusto de gerenciamento de conhecimento para agentes IA, bem pensado para arquiteturas que precisam de abstração entre ferramentas e agentes. Requer familiaridade com CLI e boas práticas de organização, mas oferece valor estratégico em pipelines complexos.

README

A tradução para o português deste README ainda está na fila.

akm — Agent Knowledge Management

npm version CI license

A package manager for AI agent capabilities — scripts, skills, commands, agents, knowledge, memories, workflows, wikis, vaults, lessons, and scheduled tasks — that works with any AI coding assistant that can run shell commands.

akm gives agents a curated, searchable library built from local directories, GitHub repos, npm packages, and websites. Instead of front-loading a giant prompt, agents pull exactly what they need, when they need it, and feed results back so the library improves over time.

Install

Option 1 — Prebuilt binary (recommended, no runtime required):

# Linux / macOS
curl -fsSL https://github.com/itlackey/akm/releases/latest/download/install.sh | bash

# Windows (PowerShell)
irm https://github.com/itlackey/akm/releases/latest/download/install.ps1 | iex

Option 2 — Bun (requires Bun >= 1.0):

bun install -g akm-cli

Upgrade in place: akm upgrade

AKM 0.8 requires the Bun runtime or the prebuilt binary. Node.js is not supported in this release. Cross-runtime compatibility is planned for 0.9.0. See Privacy & data for details on what akm stores locally.

From source (contributors only)

git clone https://github.com/itlackey/akm.git
cd akm
bun install
bun run build

What akm does

  • Manage sources — add local dirs, git repos, npm packages, and websites as searchable asset sources (details)
    akm add github:owner/stash        # GitHub
    akm add https://docs.example.com  # crawled website
    
  • Search a unified index — one FTS5 index across all your sources (details)
    akm search "deploy" --type script --limit 5
    
  • Curate a shortlist — get the best-match assets for a task without knowing exact names (details)
    akm curate "set up a kubernetes deployment"
    
  • Load assets on demand — show the full content of any asset by ref (details)
    akm show workflow:ship-release
    
  • Capture local knowledge — save discoveries as memories, imported docs, or wiki pages (details)
    akm remember "Staging deploys require VPN"
    akm import ./notes/runbook.md --wiki ops
    
  • Run structured workflows — parse, start, step through, and resume multi-step procedures (details)
    akm workflow start workflow:onboarding
    
  • Improve continuously — feedback drives proposals; proposals drive asset quality (details)
    akm feedback skill:code-review --positive
    akm improve && akm proposal list
    

Quick start

akm setup                             # guided first-time setup
akm add github:itlackey/akm-stash     # install the official onboarding stash
akm index                             # build the search index
akm curate "deploy"                   # get a curated shortlist
akm show workflow:deploy              # load the best match
akm remember "Deployment needs VPN"  # capture a memory
akm feedback workflow:deploy --positive

For non-interactive setup: akm setup --yes (or --dir ~/custom-stash for a custom path).

See docs/getting-started.md for a full walkthrough.

Asset types

TypeWhat it isExample ref
scriptExecutable shell or code automationscript:deploy.sh
skillA set of agent instructionsskill:code-review
commandA prompt template with placeholderscommand:summarize
agentSystem prompt + model + tool policyagent:reviewer
knowledgeA reference documentknowledge:api-guide
vaultKey/value environment config (keys only, never secrets)vault:prod-env
workflowStructured multi-step procedure with resumable run stateworkflow:ship-release
wikiA page inside a multi-wiki knowledge basewiki:ops/runbook
lessonDistilled feedback insightlesson:prefer-dry-run
memoryRecalled context from a previous sessionmemory:vpn-note

See docs/concepts.md for classification rules and the ref format.

Key workflows

Add and search a stash

akm add github:owner/team-stash
akm index
akm search "database migration" --type script
akm show script:migrate.sh

Capture and route knowledge

akm remember "Hot-fix deploys skip staging" --target team-stash
akm import ./incident-report.md --wiki ops
akm wiki create ops

Build a living wiki (Karpathy LLM wiki pattern)

akm wiki create research                   # scaffold wikis/research/ with schema/index/log/raw/
akm wiki stash research https://arxiv.org/abs/2404.01744  # fetch raw source into raw/
akm wiki stash research ./notes/meeting.md # stash local notes as immutable raw
akm wiki ingest research                   # dispatch defaults.agent to run the ingest workflow end-to-end

akm implements Andrej Karpathy's LLM wiki pattern: raw sources live in raw/ (immutable), the agent writes synthesized pages alongside them, and a schema.md rulebook keeps the voice and structure consistent across sessions. akm surfaces paths and invariants; your agent does the writing. See docs/wikis.md.

Improvement loop

akm feedback skill:planner --negative --reason "Doesn't account for merge conflicts"
akm improve                   # generate proposals from feedback + history
akm proposal list             # review pending proposals
akm proposal accept <uuid-or-ref>   # apply a proposal
akm proposal reject <uuid-or-ref>   # discard it

Clone and customize an asset

akm clone workflow:ship-release --dest ./project/.claude
# edit the local copy — it wins in subsequent searches automatically

The improvement loop

akm tracks which assets agents actually use (select events) and what agents think of them (akm feedback). Running akm improve processes that signal to generate proposals — suggested edits, promotions, or deprecations. Review with akm proposal list, then akm proposal accept or akm proposal reject. Accepted changes write back to your writable sources. Distilled lessons surface via akm improve --distill.

Tell your agent about akm

Add this to your AGENTS.md, CLAUDE.md, or system prompt:

## Resources & Capabilities

You have access to a searchable library of scripts, skills, commands, agents,
knowledge, workflows, vaults, wikis, lessons, and memories via the `akm` CLI.
Use `akm -h` for details.

No plugins or SDKs required. Platform-specific integrations are available in akm-plugins.

Ecosystem

RepoWhat it is
itlackey/akm-stashOfficial stash — ready-made skills, workflows, commands, and knowledge
itlackey/akm-pluginsOptional editor and agent integrations (OpenCode, etc.)
itlackey/akm-registryOfficial registry index — pre-configured in every akm install
itlackey/akm-benchBenchmark harness for measuring agent performance with akm
itlackey/akm-evalEval framework and tools for akm asset quality

Documentation

Features

FeatureDescription
Search & DiscoveryBuild the index, search, curate a shortlist, and load assets by ref
Knowledge ManagementCapture memories, import docs, manage wikis, and store config in vaults
Sources & RegistriesConnect local dirs, git repos, npm packages, and websites; browse the registry
WorkflowsStructured multi-step procedures with resumable run state
The Improvement LoopFeedback, history, proposals, and automated asset improvement
Agent IntegrationWire akm into Claude Code, OpenCode, Cursor, and other coding assistants

Reference docs

DocDescription
Getting StartedInstall, first-time setup, add sources, search, show
ConceptsSources, registries, asset types, refs, and the stash
CLI ReferenceAll commands and flags
ConfigurationSettings, providers, embedding, and Ollama setup
Stash Maker's GuideBuild, publish, and share your own stashes
RegistryRegistries, the index format, and private registry setup
WikisMulti-wiki knowledge bases
Release Notes — 0.8.0Latest release notes and migration guide
Stability policyWhich CLI surfaces are stable, evolving, or experimental
Security policyThreat model and how to report vulnerabilities
ChangelogPer-release behavior changes

Privacy & data

AKM stores data locally and has no remote telemetry. Events, proposals, and improve history are written to ~/.local/share/akm/state.db. Registry packages and config backups go to ~/.cache/akm/. Nothing leaves your machine except requests to sources you explicitly configure (GitHub, npm, your own LLM endpoint).

See docs/data-and-telemetry.md for the complete on-disk inventory, event type reference, and instructions for inspecting or clearing local data.

License

MPL-2.0

Ver o original no GitHub

Bom para

Relacionados